Learning Theory: 18th Annual Conference on Learning Theory, COLT 2005, Bertinoro, Italy, June 27-30, 2005, Proceedings
Peter Auer, Ron Meir
Springer, Aug 11, 2005 - Computational learning theory - 692 pages
This book constitutes the refereed proceedings of the 18th Annual Conference on Learning Theory, COLT 2005, held in Bertinoro, Italy in June 2005. The 45 revised full papers together with three articles on open problems presented were carefully reviewed and selected from a total of 120 submissions. The papers are organized in topical sections on: learning to rank, boosting, unlabeled data, multiclass classification, online learning, support vector machines, kernels and embeddings, inductive inference, unsupervised learning, generalization bounds, query learning, attribute efficiency, compression schemes, economics and game theory, separation results for learning models, and survey and prospects on open problems.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Learning to Rank
Learnability of Bipartite Ranking Functions
44 other sections not shown
Other editions - View all
accumulation order AdaBoost analysis approximation assume assumption Ballseptron binary bipartite ranking boosting algorithm Borel branching program co-training complexity Computational Learning Theory conjectures consider consistent constant convex Corollary define definition denote distribution empirical experts finite Gaussian given Gram matrix graph Hadamard matrix hypothesis space implies inequality iteration kernel labeled examples language learnability learning algorithm Learning Theory Lemma loss function lower bound M. K. Warmuth Machine Learning margin matrix methods mind change minimizes mistake bound multi-armed bandit multiclass node notation obtain online algorithm optimal output pairs parameter payoffs Perceptron Perceptron algorithm prediction probability at least proof random variable randomized classifier RankBoost ranking algorithm ranking function ranking problem regret result sample Schapire sequence subset support vector machines SVMs target function Theorem uniform convergence unlabeled data update upper bound VC dimension Warmuth weak learner weight vector